Voiceover & Narration Studio
Many voice needs, one clear starting point
Voiceover & Narration Studio turns prepared scripts into ready-to-edit AI narration in a library voice, a saved voice, or a custom brand voice cloned from a clean sample. It covers short-video voiceover, course narration, audiobooks delivered by chapter, multilingual and Cantonese text to speech, and recurring brand audio, delivered as MP3 by default or as WAV, FLAC, or Opus. Voiceover & Narration Studio works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Voiceover & Narration Studio and tell me when I need to sign in: https://beatra.ai/skills/voiceover-narration-studio/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.GitHub ↗Docs ↗
One clear path from script to usable audio
Choose the right route first
Start with a single voiceover, ordered long-form work, supplied multilingual scripts, or a reusable custom voice and keep each route easy to follow.
Use a current voice
Compare only voices that fit the language and use, and keep a selected voice consistent across continuing content.
Keep long-form audio organized
Arrange chapters, lessons, languages, and recurring reads in a clear sequence so every delivered audio item is easy to find and edit.
How it is made
Match the workflow to the audio you need
Keep one-off reads, ordered long-form work, supplied language versions, and custom-voice creation clear before production begins.
Choose from the current voice library or reuse a saved voice · Prepare the script so it reads naturally · Move to a focused workflow when the job is already clear
Compare only voices that fit the job
Use the selected voice across continuing work and compare the current preview whenever one is available.
Compare only genuinely suitable voice candidates · Keep the selected voice for continuing content · Use the current preview whenever it is available
Know the text, order, and current estimate first
Every audio item starts from a prepared script, with the output plan and current price estimate clear before creation.
Use prepared text for every audio item · Review the current estimate before production · Deliver long-form audio by chapter and multilingual audio by language
Keep strong audio and refine one passage at a time
Compare the delivered audio with the script and voice direction, preserve the strongest passages, and focus each revision on one clear section.
Compare each result with the script · Preserve the strongest audio · Refine one passage at a time
A creator's voice workspace
Short-video voiceover
Turn a script into one ready-to-edit read with a voice and pace chosen for the audience.
Audiobooks and course narration
Pilot a supplied passage, then keep chapters or lessons ordered with one accepted narrator.
Supplied multilingual scripts
Choose a suitable voice for each prepared language version and keep the resulting audio grouped by language and section.
A reusable brand voice
Create a named custom voice from a clean sample, then choose it again for later narration.
Inputs and outputs
Input · Text — A prepared script, its language, and the voice you want
Input · Audio — Clean sample for a custom brand voice (optional)
- Formats
- MP3, WAV
- Specifications
- 10–300 s; up to 20 MB each
Output · Audio — Ready-to-edit narration, by chapter for long-form and by language for multilingual work
- Formats
- MP3, WAV, FLAC, OPUS
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Text — A prepared script, its language, and the voice you want | — | — |
| Input | Audio — Clean sample for a custom brand voice (optional) | MP3, WAV | 10–300 s; up to 20 MB each |
| Output | Audio — Ready-to-edit narration, by chapter for long-form and by language for multilingual work | MP3, WAV, FLAC, OPUS | — |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Install tested in Claude Code, Codex, Gemini CLI, GitHub Copilot CLI, Grok CLI, and Antigravity CLI. All results
Questions
What can I make in the Voice Studio?
You can make a single voiceover, ordered audiobook or course narration, audio from supplied multilingual scripts, or a reusable custom voice for later narration.
How many languages are available?
Forty, including Mandarin Chinese and Cantonese, each read in a voice that supports that language.
Can I use my own voice?
Yes. A clean single-speaker sample becomes a named custom voice for later narration, courses, updates, and recurring brand content.
How are long-form and multilingual projects delivered?
In separate files by chapter, lesson, language, or market.
Related Skills
